The database of free AI tools on GitHub

Converts images and PDFs into structured data for LLMs.

Perform object detection, instance segmentation, and image classification using YOLO models.

Object detection, image segmentation, and image classification using PyTorch.

Build computer vision tools with reusable components and models.

Free, offline OCR software for text recognition from images and PDFs.

Extract text from images using JavaScript.

Cross-platform ML solutions for live and streaming media processing.

OCR tool for extracting text from images in multiple languages.

PyTorch implementation of Vision Transformer for image classification.

使用图像识别技术一键完成明日方舟游戏日常任务。

Facial recognition and attribute analysis library for Python.

Open-source data annotation platform for image, video, audio, and 3D datasets.

Annotate images with polygons, rectangles, and more for computer vision tasks.

识别各种类型的验证码，包括数字字母组合、中文验证码和滑块验证码。

Node-based visual programming for 3D reconstruction and image processing.

Provides advanced methods for explaining AI model predictions in computer vision.

OCR model for complex documents and forms with layout preservation.

轻量级中文 OCR 项目，支持文本检测与识别。

Provides PyTorch models for image semantic segmentation.

Unified cross-platform desktop app for annotating text, images, videos, and point clouds.

Real-time object detection using YOLOv3 models.

Translate text in manga and images.

提取视频中的硬字幕并生成srt文件。

Document image parsing using heterogeneous anchor prompting.

OCR tool for complex document understanding and real-world scenarios.

Provides Go bindings for OpenCV computer vision library.

ML-powered manga translator with OCR and inpainting for local manga translation.

Perform OCR using deep learning models for document text recognition.

Perform large-scale object detection and instance segmentation with sliced inference.

Capture text from images and screenshots using OCR on Windows.